Home

Bio

I am a Senior Manager of Applied Science at Amazon AGI, leading the computer vision organization, working on generative AI and focused at training the large-scale MLLMs powering the Amazon Nova family of models. My research interests lie in the development of advanced, multimodal large foundational models that can understand and reason about the visual world. My goal is to build cutting-edge AI to create tangible value for customers. I’m driven by the challenge of developing models that not only solve complex technical problems but also translate into real-world benefits, enhancing user experiences and enabling new possibilities for a wide range of applications. This passion for practical, customer-centric innovation has been the cornerstone of my work at Amazon over the past 9 years. Before Amazon AGI, I was a scientist/tech lead/manager in Amazon Go and Amazon Rekognition.

Prior to joining Amazon, I was a PhD student at the University of Edinburgh under the supervision of Dr. Vittorio Ferrari, a Master student at the University of Amsterdam and a Bachelor student and the University of Padova.

Amazon AGI

I am looking for passionate, talented, and inventive scientists with a strong computer vision background, to lead the development of industry-leading technology on large-scale multimodal models. Interested? Apply here for a position in my team:

• Senior Applied Scientist
• Applied Science Manager

I am hiring in Seattle, Bellevue, Sunnyvale, San Francisco, New York, Boston

News

• November 2025: I will serve as Senior Area Chair for ECCV 2026
• November 2025: Our paper on Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models was accepted at WACV 2026
• October 2025: Me and my team launched Nova Multimodal Embeddings, the first enterprise embedding model that supports customer use cases for five modalities as input!
• July 2025: I will serve as Area Chair for CVPR 2026
• February 2025: Our paper on Enhancing Numerical Prediction of MLLMs with Soft Labeling was accepted at CVPR 2025
• February 2025: I will serve as Area Chair for ICCV 2025
• September 2024: I will serve as Area Chair for CVPR 2025
• March 2024: I will serve as Area Chair for ECCV 2024
• March 2024: Five papers accepted for publication at CVPR 2024:
  • Self supervised multi object tracking with path consistency (Spotlight)
  • Hyperbolic Learning with Synthetic Captions for Open-World Detection
  • SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processes  (workshop)
  • Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity (workshop)
  • Prompting Foundational Models for Omni-supervised Instance Segmentation (workshop)
• for more publications, visit the publication tab

(website updated on 12/29/2025)